© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 95181
    Prev
    Next
    INDEX
    Explanations

    scientific/technical

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    e
    -0.55
    iling
    -0.52
     volt
    -0.51
    don
    -0.50
    a
    -0.48
    mpar
    -0.48
    ]<=
    -0.46
    aren
    -0.45
    ]!=
    -0.45
     clerk
    -0.45
    POSITIVE LOGITS
     Мексичка
    0.81
    MLLoader
    0.75
    ⓧ
    0.69
    rungsseite
    0.65
    acquisto
    0.64
    期刊论文
    0.63
     Dernière
    0.63
    uxta
    0.62
     ویکی‌پدیا
    0.61
    giveness
    0.61
    Activations Density 0.390%

    No Known Activations